Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Teachable Machine: Teach a machine using your camera, live in the browser

blog.google

Post reply on HN
Print view View original

81–90 of 95 posts

Re: Teachable Machine: Teach a machine using your camera, live in the browser

#81

Post by xyrnoble »

melling wrote: post #46
colmvp wrote: post #43

Earlier quoted context omitted.

Yeah it's a little hilarious how people just keep giving Facebook more and more data to experiment with.

HN discussions tend to devolve into rants about privacy. There are a lot of repeated discussions that occur here. They overwhelm the discussion about the actual technology https://h4labs.wordpress.com/2017/09/27/groundhog-day-amazon...

I can solve the privacy problem by not using their products? I disagree: https://en.m.wikipedia.org/wiki/FBI–King_suicide_letter

Also, my own personal privacy is less secure if it's a relative inconvenience for employers. If everyone but me gives up their privacy then there's more pressure on me to follow suit.

The argument even doubles back on itself. If these comments aren't interesting to you... don't read them. Embrace tree-style collapsible comments.

Re: Teachable Machine: Teach a machine using your camera, live in the browser

#82

Post by haser_au »

nsthorat wrote: post #54

deeplearn.js author here... We do not send any webcam / audio data back to a server, all of the computation is totally client side. The storage API requests are just downloading weights of a pretrained model. We're thinking about releasing a blog post explaining the technical details of this project, would people be interested?

A blog post on the technical details would be great, please. Thanks in advance, since I know it'll take a bit of your time to write.

Re: Teachable Machine: Teach a machine using your camera, live in the browser

#83

Post by haser_au »

greggman wrote: post #11

be aware, at least in Chrome, once you give teachablemachine.withgoogle.com permission to use you camera, unless you revoke that permission is has permission to use your camera without further permission including from iframes. In other words every ad from and analytics from Google could start injecting camera access. I wish chrome would give the option to only give permission "this time" and I wish it didn't allow c…

Chrome does give you this option. It's called "incognito mode"

Re: Teachable Machine: Teach a machine using your camera, live in the browser

#84

Post by greggman »

jamesmishra wrote: post #42
greggman wrote: post #11

be aware, at least in Chrome, once you give teachablemachine.withgoogle.com permission to use you camera, unless you revoke that permission is has permission to use your camera without further permission including from iframes. In other words every ad from and analytics from Google could start injecting camera access. I wish chrome would give the option to only give permission "this time" and I wish it didn't allow c…

If this happened, the Google Chrome tab would show a camera. Many webcams have adjacent LEDs that identify that they are activated. Google could theoretically release compromised versions of Google Chrome and only use the permission on devices where webcam LEDs are unlikely (e.g. smartphones), but this is going deep into tin-foil-hat territory.

that's not helpful. the pictures would already be taken and uploaded to servers without my permission reguardless of whether or not I wanted my picture taken or what's visible (contracts, trade secrets, people in various states of undress) .

also this isn't about Google spying. it's about Chrome's bad camera permission model. any company can abuse it

Re: Teachable Machine: Teach a machine using your camera, live in the browser

#85

Post by jamesmishra »

runj__ wrote: post #60
jamesmishra wrote: post #41

Earlier quoted context omitted.

The faces are unlabeled, and I'm not sure what that data would be good for. If Google really wanted face data, they could look at: - Gmail / Google Plus / Google Apps profile pictures - Google Street View - Google Hangouts - implementing a primitive Face ID or Snapchat-style camera on Google Android - the large mass of face pictures that they index with Google Images

Google Photos seems like the absolute best bet there, they're "organizing" them there by default.

Can't believe I forgot about that one! I'm an avid Google Photos user, and they definitely have some pretty amazing unsupervised clustering for faces.

Re: Teachable Machine: Teach a machine using your camera, live in the browser

#86

Post by melling »

xyrnoble wrote: post #81
melling wrote: post #46

Earlier quoted context omitted.

HN discussions tend to devolve into rants about privacy. There are a lot of repeated discussions that occur here. They overwhelm the discussion about the actual technology https://h4labs.wordpress.com/2017/09/27/groundhog-day-amazon...

I can solve the privacy problem by not using their products? I disagree: https://en.m.wikipedia.org/wiki/FBI–King_suicide_letter Also, my own personal privacy is less secure if it's a relative inconvenience for employers. If everyone but me gives up their privacy then there's more pressure on me to follow suit. The argument even doubles back on itself. If these comments aren't interesting to you... don't read them. E…

The comments are repetitive and are basically complaining. If there was something to be learned that would make it useful and interesting.

Re: Teachable Machine: Teach a machine using your camera, live in the browser

#87

Post by eggie5 »

nsthorat wrote: post #59
amelius wrote: post #55

Earlier quoted context omitted.

Yes please! :) And some quick questions: What network topology do you use, and on what model is it based (e.g. "inception")? What kind of data have you used to pretrain the model?

We're using SqueezeNet ( https://github.com/DeepScale/SqueezeNet ), which is similar to Inception (trained on the same ImageNet dataset) but is much smaller - 5MB instead of inception's 100MB - and inference is much much quicker. The application takes webcam frames and infers through SqueezeNet, producing a 1000D logits vector for each frame. These can be thought of as unnormalized probabilities for each of ImageNet'…

So you're doing nearest neighbour search on the images features from the CNN. This is alluded to in Figure 4 of the DeCaf paper: https://twitter.com/eggie5/status/907120374575505408

Re: Teachable Machine: Teach a machine using your camera, live in the browser

#88

Post by sydd »

nsthorat wrote: post #54

deeplearn.js author here... We do not send any webcam / audio data back to a server, all of the computation is totally client side. The storage API requests are just downloading weights of a pretrained model. We're thinking about releasing a blog post explaining the technical details of this project, would people be interested?

Why does it not work in Edge? Please keep the web open, do not make stuff that does not work in a modern browser. Also always give an option to try it anyway.

Re: Teachable Machine: Teach a machine using your camera, live in the browser

#89

Post by eggie5 »

eggie5 wrote: post #87
nsthorat wrote: post #59

Earlier quoted context omitted.

We're using SqueezeNet ( https://github.com/DeepScale/SqueezeNet ), which is similar to Inception (trained on the same ImageNet dataset) but is much smaller - 5MB instead of inception's 100MB - and inference is much much quicker. The application takes webcam frames and infers through SqueezeNet, producing a 1000D logits vector for each frame. These can be thought of as unnormalized probabilities for each of ImageNet'…

So you're doing nearest neighbour search on the images features from the CNN. This is alluded to in Figure 4 of the DeCaf paper: https://twitter.com/eggie5/status/907120374575505408

alexnet paper not decaf paper!

Re: Teachable Machine: Teach a machine using your camera, live in the browser

#90

Post by godelmachine »

nsthorat wrote: post #54

deeplearn.js author here... We do not send any webcam / audio data back to a server, all of the computation is totally client side. The storage API requests are just downloading weights of a pretrained model. We're thinking about releasing a blog post explaining the technical details of this project, would people be interested?

To answer the question at last, yes, I am interested.
Post reply on HN